Prediction of treatment adaptation based on pca modeling of head and neck anatomy using daily CBCT images.

Authors

Panagiotis Tsiamas, Henry Ford Health
Hassan Bagher-Ebadian, Henry Ford HealthFollow
Farzan Siddiqui, Henry Ford HealthFollow
Chang Liu, Henry Ford HealthFollow
C Hvid, Henry Ford Health
Stephen L. Brown, Henry Ford HealthFollow
M Benjamin, Henry Ford Health
Indrin J. Chetty, Henry Ford HealthFollow

Recommended Citation

Tsiamas P, Bagher-Ebadian H, Siddiqui F, Liu C, Hvid C, Brown S, Benjamin M, and Chetty I. Prediction of treatment adaptation based on pca modeling of head and neck anatomy using daily CBCT images. Med Phys 2018; 45(6):e486.

Document Type

Conference Proceeding

Publication Date

2018

Publication Title

Med Phys

Abstract

Purpose: To model head/neck anatomy from daily CBCT images over the course of fractionated radiotherapy using Principal Component Analysis (PCA). Methods: Eighteen oropharyngeal head-and-neck cancer patients, treated with VMAT, were included in this retrospective study. Normal organs, including the parotid and submandibular glands, mandible, pharyngeal constrictor muscles (PCMs), and spinal cord were contoured using daily CBCT image datasets. PCA models for each organ were developed for individual patients (IP) and the entire patient cohort/population (PP). The first 10 principal components (PCs) were extracted for all models. Analysis included cumulative and individual PCs for each organ and patient, as well as the aggregate organ/patient population; comparisons were made using the rootmean- square (RMS) of the percentage predicted spatial displacement for each PC. Results: Overall, spatial displacement prediction was achieved at the 95% confidence level (CL) for the first 3-4 PCs for all organs, based on IP models. For PP models, the first 4 PC's predicted spatial displacement at the 80-90% CL. Differences in percentage predicted spatial displacement between mean IP models for each organ ranged from 2.8% ± 1.8% (1st PC) to 0.6% ± 0.4% (4th PC). Differences in percentage predicted spatial displacement between IP models vs the mean IP model for each organ based on the 1st PC were <12.9% ± 6.9% for all organs. Differences in percentage predicted spatial displacement between IP and PP models based on all organs and patients for the 1st and 2nd PC were <11.7% ± 2.2%. Conclusion: Tissue changes during fractionated radiotherapy observed on daily CBCT in patients with head/neck cancers, were modeled using PCA. In general, spatial displacement for organs-at-risk were predicted for the first 4 PCs at the 95% CL, for IP models, and at the 80-90% CL for PP models. The IP and PP models were most predictive of changes in glandular organs and pharyngeal constrictor muscles, respectively.

Volume

45

Issue

6

First Page

e486